Will there be faster code for PPC (he asked with despair in his eyes)?
Sorry - didn't throughly read the title...
I am working on it. The App for G5 PPC that's on our Power User page is meant as a first step.
However, I'm not much of a prophet, and if there's one thing I learned from recent coding, it's that it's almost impossible to predict the speedup a particular change would make on a certain CPU. One feature I'm desperately missing in the AltiVec / Velocity Engine (compared to SSE2 on x86) is double precision calculation. We'll see how far I can get with PPC.
Will there be faster code for PPC (he asked with despair in his eyes)?
I couldn't see his machines, as he has them hidden.
I am working on it. The App for G5 PPC that's on our Power User page is meant as a first step.
However, I'm not much of a prophet, and if there's one thing I learned from recent coding, it's that it's almost impossible to predict the speedup a particular change would make on a certain CPU. One feature I'm desperately missing in the AltiVec / Velocity Engine (compared to SSE2 on x86) is double precision calculation. We'll see how far I can get with PPC.
Will there be faster code for PPC (he asked with despair in his eyes)?
Sorry - didn't throughly read the title...
I am working on it. The App for G5 PPC that's on our Power User page is meant as a first step.
However, I'm not much of a prophet, and if there's one thing I learned from recent coding, it's that it's almost impossible to predict the speedup a particular change would make on a certain CPU. One feature I'm desperately missing in the AltiVec / Velocity Engine (compared to SSE2 on x86) is double precision calculation. We'll see how far I can get with PPC.
We've seen a ~17% decrease in credit awarded per work unit yet speedups have been 30%+ ??? Not that i mind the extra credit.
The reason they're not a 1:1 corespondence is that only x86/SSE (win/linux) were improved by the apps that just went official. X86 NonSSE (mainly older athlon's), mac's, and other *nix platforms saw no speedup. When the current G5 power user app goes live credit/WU will drop again bringing it closer to the old levels for platforms with improved apps. The ones still code dating to the start of S5 will still preclude a complete shift in credit/hour back to the original values.
Credits per unit dropped from 19.94 to 16.53 on Mac PPC G4, why?
)
Yep. We need to adjust the credit so that we stay on the same level of credit/hour as the other BOINC projects.
BM
BM
RE: Is this because of the
)
Yes.
Michael
Team Linux Users Everywhere
RE: Yep. We need to adjust
)
Will there be faster code for PPC G4 (he asked with despair in his eyes)?
RE: Will there be faster
)
Sorry - didn't throughly read the title...
I am working on it. The App for G5 PPC that's on our Power User page is meant as a first step.
However, I'm not much of a prophet, and if there's one thing I learned from recent coding, it's that it's almost impossible to predict the speedup a particular change would make on a certain CPU. One feature I'm desperately missing in the AltiVec / Velocity Engine (compared to SSE2 on x86) is double precision calculation. We'll see how far I can get with PPC.
BM
BM
RE: RE: Will there be
)
Power Macintosh PowerMac6,4
Darwin 7.9.0
RE: RE: Will there be
)
Thanks!
We've seen a ~17% decrease in
)
We've seen a ~17% decrease in credit awarded per work unit yet speedups have been 30%+ ??? Not that i mind the extra credit.
RE: We've seen a ~17%
)
The reason they're not a 1:1 corespondence is that only x86/SSE (win/linux) were improved by the apps that just went official. X86 NonSSE (mainly older athlon's), mac's, and other *nix platforms saw no speedup. When the current G5 power user app goes live credit/WU will drop again bringing it closer to the old levels for platforms with improved apps. The ones still code dating to the start of S5 will still preclude a complete shift in credit/hour back to the original values.
RE: We've seen a ~17%
)
I don't mid extra credit at all too. :D
But why all this cross project credit calibrating stuff ???
Why can't we leave it the way it is ?
RE: RE: We've seen a ~17%
)
To avoid a credit war between projects, and the attendant flaming wars that would accompany it.